Skip to content

Instantly share code, notes, and snippets.

Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save plebeau/8380a8804df21462cf5d to your computer and use it in GitHub Desktop.
Save plebeau/8380a8804df21462cf5d to your computer and use it in GitHub Desktop.
Galaxy RNAseq workflow for Martin Cech
{
"a_galaxy_workflow": "true",
"annotation": "StandaredPaired",
"format-version": "0.1",
"name": "SingleReadGrCH38wDups_TopHatAnnotationTest",
"steps": {
"0": {
"annotation": "",
"id": 0,
"input_connections": {},
"inputs": [
{
"description": "",
"name": "fastq input"
}
],
"name": "Input dataset",
"outputs": [],
"position": {
"left": 285,
"top": 206
},
"tool_errors": null,
"tool_id": null,
"tool_state": "{\"name\": \"fastq input\"}",
"tool_version": null,
"type": "data_input",
"user_outputs": []
},
"1": {
"annotation": "",
"id": 1,
"input_connections": {},
"inputs": [
{
"description": "",
"name": "ribosomal intervals"
}
],
"name": "Input dataset",
"outputs": [],
"position": {
"left": 1162,
"top": 810
},
"tool_errors": null,
"tool_id": null,
"tool_state": "{\"name\": \"ribosomal intervals\"}",
"tool_version": null,
"type": "data_input",
"user_outputs": []
},
"2": {
"annotation": "",
"id": 2,
"input_connections": {},
"inputs": [
{
"description": "",
"name": "genome reflat"
}
],
"name": "Input dataset",
"outputs": [],
"position": {
"left": 1161,
"top": 882
},
"tool_errors": null,
"tool_id": null,
"tool_state": "{\"name\": \"genome reflat\"}",
"tool_version": null,
"type": "data_input",
"user_outputs": []
},
"3": {
"annotation": "",
"id": 3,
"input_connections": {},
"inputs": [
{
"description": "",
"name": "gff/gtf file"
}
],
"name": "Input dataset",
"outputs": [],
"position": {
"left": 1611,
"top": 296
},
"tool_errors": null,
"tool_id": null,
"tool_state": "{\"name\": \"gff/gtf file\"}",
"tool_version": null,
"type": "data_input",
"user_outputs": []
},
"4": {
"annotation": "",
"id": 4,
"input_connections": {
"input_file": {
"id": 0,
"output_name": "output"
}
},
"inputs": [],
"name": "FASTQ Trimmer",
"outputs": [
{
"name": "output_file",
"type": "input"
}
],
"position": {
"left": 474,
"top": 206
},
"post_job_actions": {
"HideDatasetActionoutput_file": {
"action_arguments": {},
"action_type": "HideDatasetAction",
"output_name": "output_file"
}
},
"tool_errors": null,
"tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/fastq_trimmer/fastq_trimmer/1.0.0",
"tool_state": "{\"__page__\": 0, \"keep_zero_length\": \"\\\"False\\\"\", \"__rerun_remap_job_id__\": null, \"input_file\": \"null\", \"offset_type\": \"{\\\"right_column_offset\\\": \\\"1\\\", \\\"left_column_offset\\\": \\\"0\\\", \\\"base_offset_type\\\": \\\"offsets_absolute\\\", \\\"__current_case__\\\": 0}\"}",
"tool_version": "1.0.0",
"type": "tool",
"user_outputs": []
},
"5": {
"annotation": "",
"id": 5,
"input_connections": {
"input_file": {
"id": 0,
"output_name": "output"
}
},
"inputs": [],
"name": "FastQC: Comprehensive QC",
"outputs": [
{
"name": "html_file",
"type": "html"
}
],
"position": {
"left": 1369,
"top": 963
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/fastqc/fastqc/0.53",
"tool_state": "{\"__page__\": 0, \"contaminants\": \"null\", \"__rerun_remap_job_id__\": null, \"out_prefix\": \"\\\"FastQC\\\"\", \"input_file\": \"null\"}",
"tool_version": "0.53",
"type": "tool",
"user_outputs": []
},
"6": {
"annotation": "",
"id": 6,
"input_connections": {
"input_file": {
"id": 4,
"output_name": "output_file"
}
},
"inputs": [],
"name": "FASTQ Quality Trimmer",
"outputs": [
{
"name": "output_file",
"type": "input"
}
],
"position": {
"left": 691,
"top": 203
},
"post_job_actions": {
"HideDatasetActionoutput_file": {
"action_arguments": {},
"action_type": "HideDatasetAction",
"output_name": "output_file"
}
},
"tool_errors": null,
"tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/fastq_trimmer_by_quality/fastq_quality_trimmer/1.0.0",
"tool_state": "{\"__page__\": 0, \"score_comparison\": \"\\\">=\\\"\", \"window_size\": \"\\\"1\\\"\", \"trim_ends\": \"\\\"53\\\"\", \"input_file\": \"null\", \"__rerun_remap_job_id__\": null, \"aggregation_action\": \"\\\"min\\\"\", \"quality_score\": \"\\\"30.0\\\"\", \"step_size\": \"\\\"1\\\"\", \"keep_zero_length\": \"\\\"False\\\"\", \"exclude_count\": \"\\\"0\\\"\"}",
"tool_version": "1.0.0",
"type": "tool",
"user_outputs": []
},
"7": {
"annotation": "",
"id": 7,
"input_connections": {
"input1": {
"id": 6,
"output_name": "output_file"
}
},
"inputs": [],
"name": "Tophat for Illumina",
"outputs": [
{
"name": "insertions",
"type": "bed"
},
{
"name": "deletions",
"type": "bed"
},
{
"name": "junctions",
"type": "bed"
},
{
"name": "accepted_hits",
"type": "bam"
}
],
"position": {
"left": 932,
"top": 203
},
"post_job_actions": {
"HideDatasetActionaccepted_hits": {
"action_arguments": {},
"action_type": "HideDatasetAction",
"output_name": "accepted_hits"
},
"HideDatasetActiondeletions": {
"action_arguments": {},
"action_type": "HideDatasetAction",
"output_name": "deletions"
},
"HideDatasetActioninsertions": {
"action_arguments": {},
"action_type": "HideDatasetAction",
"output_name": "insertions"
},
"HideDatasetActionjunctions": {
"action_arguments": {},
"action_type": "HideDatasetAction",
"output_name": "junctions"
}
},
"tool_errors": null,
"tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/tophat/tophat/1.5.0",
"tool_state": "{\"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input1\": \"null\", \"refGenomeSource\": \"{\\\"genomeSource\\\": \\\"indexed\\\", \\\"index\\\": \\\"GRCh38\\\", \\\"__current_case__\\\": 0}\", \"singlePaired\": \"{\\\"sParams\\\": {\\\"sSettingsType\\\": \\\"preSet\\\", \\\"__current_case__\\\": 0}, \\\"sPaired\\\": \\\"single\\\", \\\"__current_case__\\\": 0}\"}",
"tool_version": "1.5.0",
"type": "tool",
"user_outputs": []
},
"8": {
"annotation": "",
"id": 8,
"input_connections": {
"input_file": {
"id": 7,
"output_name": "accepted_hits"
}
},
"inputs": [],
"name": "Mark Duplicate reads",
"outputs": [
{
"name": "out_file",
"type": "bam"
},
{
"name": "html_file",
"type": "html"
}
],
"position": {
"left": 1119,
"top": 136
},
"post_job_actions": {
"HideDatasetActionout_file": {
"action_arguments": {},
"action_type": "HideDatasetAction",
"output_name": "out_file"
}
},
"tool_errors": null,
"tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/picard/rgPicardMarkDups/1.56.0",
"tool_state": "{\"remDups\": \"\\\"True\\\"\", \"assumeSorted\": \"\\\"True\\\"\", \"input_file\": \"null\", \"readRegex\": \"\\\"[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*\\\"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"out_prefix\": \"\\\"Dupes Marked\\\"\", \"optDupeDist\": \"\\\"100\\\"\"}",
"tool_version": "1.56.0",
"type": "tool",
"user_outputs": []
},
"9": {
"annotation": "",
"id": 9,
"input_connections": {
"input1": {
"id": 7,
"output_name": "accepted_hits"
}
},
"inputs": [],
"name": "BAM-to-SAM",
"outputs": [
{
"name": "output1",
"type": "sam"
}
],
"position": {
"left": 1405,
"top": 201
},
"post_job_actions": {
"HideDatasetActionoutput1": {
"action_arguments": {},
"action_type": "HideDatasetAction",
"output_name": "output1"
}
},
"tool_errors": null,
"tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/bam_to_sam/bam_to_sam/1.0.3",
"tool_state": "{\"header\": \"\\\"True\\\"\", \"__rerun_remap_job_id__\": null, \"input1\": \"null\", \"__page__\": 0}",
"tool_version": "1.0.3",
"type": "tool",
"user_outputs": []
},
"10": {
"annotation": "",
"id": 10,
"input_connections": {
"input_file": {
"id": 7,
"output_name": "accepted_hits"
}
},
"inputs": [],
"name": "SAM/BAM Alignment Summary Metrics",
"outputs": [
{
"name": "html_file",
"type": "html"
}
],
"position": {
"left": 1361,
"top": 641
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/picard/PicardASMetrics/1.56.0",
"tool_state": "{\"genomeSource\": \"{\\\"index\\\": \\\"GRCh38\\\", \\\"refGenomeSource\\\": \\\"indexed\\\", \\\"__current_case__\\\": 1}\", \"bisulphite\": \"\\\"False\\\"\", \"input_file\": \"null\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"out_prefix\": \"\\\"Picard Alignment Summary Metrics\\\"\", \"adaptors\": \"\\\"\\\"\", \"sorted\": \"\\\"True\\\"\", \"maxinsert\": \"\\\"100000\\\"\"}",
"tool_version": "1.56.0",
"type": "tool",
"user_outputs": []
},
"11": {
"annotation": "",
"id": 11,
"input_connections": {
"input_file": {
"id": 7,
"output_name": "accepted_hits"
},
"ref_flat": {
"id": 2,
"output_name": "output"
},
"ribosomal_intervals": {
"id": 1,
"output_name": "output"
}
},
"inputs": [],
"name": "SAM/BAM RNA Seq Metrics",
"outputs": [
{
"name": "html_file",
"type": "html"
}
],
"position": {
"left": 1366,
"top": 775
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/picard/PicardRnaSeqMetrics/1.56.0",
"tool_state": "{\"genomeSource\": \"{\\\"index\\\": \\\"GRCh38\\\", \\\"refGenomeSource\\\": \\\"indexed\\\", \\\"__current_case__\\\": 1}\", \"__page__\": 0, \"strand_specificity\": \"\\\"FIRST_READ_TRANSCRIPTION_STRAND\\\"\", \"__rerun_remap_job_id__\": null, \"input_file\": \"null\", \"out_prefix\": \"\\\"RNA Seq Metrics\\\"\", \"ref_flat\": \"null\", \"ribosomal_intervals\": \"null\"}",
"tool_version": "1.56.0",
"type": "tool",
"user_outputs": []
},
"12": {
"annotation": "",
"id": 12,
"input_connections": {
"fastq": {
"id": 0,
"output_name": "output"
},
"hits": {
"id": 9,
"output_name": "output1"
}
},
"inputs": [],
"name": "Tophat Stats PE",
"outputs": [
{
"name": "output",
"type": "txt"
}
],
"position": {
"left": 1360,
"top": 490
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "toolshed.g2.bx.psu.edu/repos/jjohnson/tophat_stats_pe/tophatstatsPE/1.0",
"tool_state": "{\"__page__\": 0, \"fastq\": \"null\", \"__rerun_remap_job_id__\": null, \"hits\": \"null\"}",
"tool_version": "1.0",
"type": "tool",
"user_outputs": []
},
"13": {
"annotation": "",
"id": 13,
"input_connections": {
"input": {
"id": 9,
"output_name": "output1"
}
},
"inputs": [],
"name": "Sort",
"outputs": [
{
"name": "out_file1",
"type": "input"
}
],
"position": {
"left": 1608,
"top": 202
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "sort1",
"tool_state": "{\"__page__\": 0, \"style\": \"\\\"alpha\\\"\", \"column\": \"{\\\"__class__\\\": \\\"UnvalidatedValue\\\", \\\"value\\\": \\\"1\\\"}\", \"__rerun_remap_job_id__\": null, \"order\": \"\\\"DESC\\\"\", \"input\": \"null\", \"column_set\": \"[]\"}",
"tool_version": "1.0.3",
"type": "tool",
"user_outputs": []
},
"14": {
"annotation": "When finished, use Join, Subtract and Group -> Column Join to create output matrix. Columns will need to be renamed.",
"id": 14,
"input_connections": {
"gfffile": {
"id": 3,
"output_name": "output"
},
"samfile": {
"id": 13,
"output_name": "out_file1"
}
},
"inputs": [],
"name": "htseq-count",
"outputs": [
{
"name": "counts",
"type": "tabular"
},
{
"name": "othercounts",
"type": "tabular"
},
{
"name": "samoutfile",
"type": "bam"
}
],
"position": {
"left": 1810,
"top": 204
},
"post_job_actions": {
"HideDatasetActionothercounts": {
"action_arguments": {},
"action_type": "HideDatasetAction",
"output_name": "othercounts"
},
"HideDatasetActionsamoutfile": {
"action_arguments": {},
"action_type": "HideDatasetAction",
"output_name": "samoutfile"
}
},
"tool_errors": null,
"tool_id": "toolshed.g2.bx.psu.edu/repos/lparsons/htseq_count/htseq_count/0.4.1",
"tool_state": "{\"featuretype\": \"\\\"exon\\\"\", \"samout_conditional\": \"{\\\"samout\\\": \\\"False\\\", \\\"__current_case__\\\": 1}\", \"singlepaired\": \"\\\"single\\\"\", \"idattr\": \"\\\"gene_id\\\"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"stranded\": \"\\\"no\\\"\", \"samfile\": \"null\", \"gfffile\": \"null\", \"minaqual\": \"\\\"0\\\"\", \"mode\": \"\\\"union\\\"\"}",
"tool_version": "0.4.1",
"type": "tool",
"user_outputs": []
}
}
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment